Scripts2026年3月30日·1 分钟阅读

Marker — Convert PDF to Markdown with High Accuracy

Fast, accurate PDF to Markdown + JSON converter. Handles tables, images, equations, code blocks, and multi-column layouts. GPU-accelerated. 33K+ GitHub stars.

Script Depot
Script Depot · Community
介绍

Marker converts PDF files to Markdown and JSON with high accuracy and speed. It correctly handles complex layouts including tables, images, equations, code blocks, multi-column text, headers/footers, and footnotes. GPU-accelerated for fast batch processing. Built on the Surya OCR engine for multi-language support. 33,000+ GitHub stars.

Best for: RAG pipelines, document ingestion, PDF data extraction, knowledge base building Works with: Any LLM pipeline — LangChain, LlamaIndex, Haystack, custom RAG systems

Key Features

Accurate Conversion

  • Tables — Preserved as Markdown tables with alignment
  • Images — Extracted and saved as separate files
  • Equations — Converted to LaTeX notation
  • Code blocks — Detected and formatted with syntax highlighting
  • Multi-column — Correctly reads multi-column layouts in order
  • Headers/footers — Automatically removed

Performance

  • GPU-accelerated — 10x faster with CUDA
  • Batch processing — Convert entire directories
  • Multi-language — 90+ languages via Surya OCR engine

Output Formats

  • Markdown (clean, LLM-ready)
  • JSON (structured with metadata)
  • HTML

Comparison

Feature Marker PyPDF pdfplumber
Tables ✅ ❌ ✅
Images ✅ ❌ ❌
Equations ✅ ❌ ❌
Multi-column ✅ ❌ ❌
OCR (scanned) ✅ ❌ ❌
Speed (GPU) Fast Fast Medium

FAQ

Q: What is Marker? A: A fast, accurate PDF to Markdown converter that handles tables, images, equations, code blocks, and multi-column layouts. GPU-accelerated with 90+ language support. 33K+ GitHub stars.

Q: Can Marker handle scanned PDFs? A: Yes, it includes OCR via the Surya engine, supporting 90+ languages for both native and scanned PDFs.

🙏

来源与感谢

Created by Datalab. Licensed under GPL-3.0. datalab-to/marker — 33,000+ GitHub stars

讨论

登录后参与讨论。
还没有评论，来写第一条吧。

相关资产

Flax — Neural Network Library for JAX

A high-performance neural network library built on JAX, providing a flexible module system used extensively across Google DeepMind and the JAX research community.

Script Depot

PyCaret — Low-Code Machine Learning in Python

An open-source AutoML library that wraps scikit-learn, XGBoost, LightGBM, CatBoost, and other ML libraries into a unified low-code interface for rapid experimentation.

Script Depot

DGL — Deep Graph Library for Scalable Graph Neural Networks

A high-performance framework for building graph neural networks on top of PyTorch, TensorFlow, or MXNet, designed for both research prototyping and production-scale graph learning.

Script Depot
◈首页🔍搜索👤我的